Toward Polymorphic Backdoor Against Semantic Communication via Intensity-Based Poisoning

Summary

Researchers propose SemBugger, a polymorphic backdoor against Semantic Communication (SC) systems. Unlike earlier monomorphic SC backdoors with a single attack target, it adjusts trigger intensity to produce diverse malicious outputs through a multi-effect poisoning-training framework, while keeping transmission fidelity for benign samples. Experiments on diverse SC models and benchmark datasets report high attack efficacy and a defense that neutralizes the attacks.

Mitigation

The paper proposes a provable robustness defense that adds controlled noise to SC inputs to resist SemBugger's homogeneous attacks, with a theoretical lower bound on defense efficacy.

Related items

• HighCVE-2026-123818: LMDeploy is a toolkit for compressing, deploying, and serving large language models. From 0.12.3 until 0.15.0…Similar attack · NVD/CVE Database
• HighGHSA-vvr2-h2jp-838m: Code Graph RAG: MCP paginated read_file path traversal / arbitrary file readSimilar attack · GitHub Advisory Database
• MediumAttackers Crash Claude's 'Office Party' Flaw to Run Malicious Code on LinuxSimilar attack · Dark Reading
• MediumCVE-2026-124588: huggingface finetrainers code injection via Library argumentSimilar attack · NVD/CVE Database
• MediumTaiwan-Based Hacker Used BOSSAI AI Agents to Steal Taipei Emergency Dispatch RecordsSimilar attack · The Hacker News